Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover readOnly, idempotent, and non-destructive. Description adds 'No auth required. No side effects' and return format, providing useful behavioral context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three efficient sentences: purpose, usage guidelines, and return format. No wasted words, front-loaded with key action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no parameters, clear annotations, and output schema described in text, the description covers all necessary context for an agent to use the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

No parameters exist; schema coverage is 100%. Description adds value by explaining the return JSON structure, which goes beyond the schema's empty properties.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool returns MCP server liveness information (version, origin, tool count, catalog size) and distinguishes from siblings by specifying not to use for business outcomes and directing to vc_* or pay tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use (hosted inspector probes, before diagnosing tool failures) and when not to (business outcomes) with named alternatives (vc_*, pay).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate openWorldHint=true and readOnlyHint=false. Description adds value by disclosing side effects ('may settle USDC via x402') and return types (payment_required with pay_to/amount). No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with a one-line summary, usage guidelines, args, and return info. Every sentence adds value, though slightly verbose in the args section. Good front-loading.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given tool complexity (3 params, 1 required, output schema exists), description covers purpose, usage guidance, side effects, return types, and error conditions. No gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. Description repeats parameter descriptions from schema but adds minimal extra context (e.g., examples for slug). Does not significantly enhance beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Call any Vibes-Coded outcome by slug' with optional payment, and distinguishes from dedicated tools like vc_web_search. It specifies the action, resource, and scope precisely.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly describes when to use (catalog outcomes without dedicated tool, retry after payment_required) and when not (instead of health). Also advises preferring prepaid keys, providing clear decision guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds 'Advisory only; no local writes' aligning with readOnly, and describes return type ('GO/NO-GO style JSON with reasons, or payment_required') and authentication requirements, providing full transparency without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Five concise sentences, each serving a purpose: purpose, usage, siblings, auth, and return. No fluff, and front-loaded with the primary use case.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (4 params, 1 required, output schema exists), the description covers purpose, usage, behavior, auth, return format, and when to avoid. No gaps remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. The description only repeats the parameter examples already in the schema (e.g., action labels). It adds no new semantic information beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: to preflight financial or external-write actions for duplicates, stale state, or unmet invariants. It distinguishes itself from siblings by naming them with specific use cases.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use ('Use before spending money or writing outside the agent sandbox') and when not to use ('Do not use for generic search — use vc_web_search'). Also references sibling tools with their purposes, providing clear alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already indicate read-only, idempotent, non-destructive. Description adds that it is advisory only, returns JSON with drifted fields and severity or payment_required, and mentions auth requirements. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Description is short, front-loaded with purpose, then usage guidelines, auth, and output. Every sentence adds value with no waste.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given output schema exists, description need not detail returns. It covers purpose, usage boundaries, auth, and output format sufficiently for a guard tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. Description adds context about return value and auth but does not detail individual parameters beyond what schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool compares current agent state to a trusted baseline and flags drifted fields. It uses specific verbs and resources, and distinguishes itself from sibling tools like vc_idempotency_guard and vc_retry_storm_guard.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use (verifying no silent changes) and when not to use (payment retries, with alternative tools named). Provides clear context for appropriate usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Discloses that it is advisory-only with no local writes, describes authentication requirements (X-Vibes-Key or x402), and states return type (JSON assessing key presence/durability or payment_required). No contradiction with annotations (readOnlyHint, idempotentHint, destructiveHint).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Concise at 6 sentences, front-loaded with purpose, no redundant information, each sentence serves a clear function.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 4 parameters (1 required), 100% schema coverage, and an output schema, the description covers purpose, usage, auth, behavior, and return format fully, leaving no significant gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, but the description adds meaning by linking the payment_signature parameter to x402 authentication, and explicitly mentions the required idempotency_key, providing context beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states the tool checks idempotency protection for paid actions, uses specific verb 'check' and resource 'paid action protected by idempotency key', and distinguishes from siblings vc_agent_state_guard and vc_retry_storm_guard.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit when-to-use ('before retrying a payment or other side-effecting call') and when-not-to-use ('Do not use for content fetch — use vc_web_search / vc_page_markdown'), and names alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations (readOnly, idempotent, non-destructive), description adds side effects (none local, compute-only), idempotency for same text, and return possibilities (repaired JSON or payment_required). No contradictions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Six sentences, each serving a distinct purpose (purpose, usage, exclusion, auth, side effects, return). Front-loaded with core action. No unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with output schema and full param coverage, description covers all aspects: purpose, usage, auth, side effects, return. Complete and self-sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with clear param descriptions. Description does not add significant extra meaning beyond what schema already provides for the two parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states it repairs malformed JSON from LLM output, with explicit examples of issues (trailing commas, missing quotes). Differentiates from siblings by specifying it is not for web fetching or search.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use (broken JSON from model) and when not to use (web fetching/search), providing alternative tool names. Also mentions auth requirements.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Beyond annotations (readOnly, idempotent, etc.), the description discloses authentication methods, side effects ('outbound HTTP GET; no local writes'), cost implications, and return format details. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Six sentences, each adding distinct value (purpose, usage, auth, side effects, return). No redundancy, well-structured, and front-loaded with key purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's low complexity (2 params, simple fetch), the description covers all necessary aspects: purpose, usage, authentication, side effects, and return. Output schema exists, so return details are not required.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds minimal new information about parameters beyond what schema already provides; the payment_signature context about auth is slightly helpful but not substantial.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action ('Fetch a public webpage') and output ('clean markdown plus extracted text'), with a specific verb and resource. It distinguishes itself from the sibling tool vc_web_search by noting the removal of the search discovery use case.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit guidance on when to use ('already have a URL'), when not to use ('not for search discovery', 'not for authenticated or paywalled pages'), and alternative tool ('call vc_web_search first').

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description declares the tool is 'Advisory only' and states it returns a 'JSON risk assessment, or payment_required', which adds behavioral context beyond the annotations (readOnlyHint, idempotentHint). It also mentions authentication requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very concise with five sentences, each providing essential information: purpose, detection details, sibling reference, auth, and output type. No redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has three parameters, clear schema descriptions, and an output schema, the description covers purpose, usage context, auth, and output type. It is complete for an AI agent to understand when and how to use it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although the description does not detail each parameter, the input schema has 100% description coverage, so it already explains the parameters. The description adds value by explaining what the tool detects (synchronized backoff, etc.), which relates to the 'retry_config' parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'Detect' with the resource 'retry configs', and clearly states what it flags (synchronized backoff, missing jitter, runaway fanout). It distinguishes itself from the sibling 'vc_idempotency_guard' by noting the different focus.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description advises using this tool 'before you enable aggressive retries on paid or rate-limited APIs', providing clear usage context. It also mentions a sibling for a different purpose. While it does not explicitly list when not to use, the context is sufficient.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds valuable context: authentication options (free-trial/prepaid X-Vibes-Key, USDC via x402), side effects (outbound HTTP, no local writes), and return behavior (JSON results or payment_required challenge). This goes beyond what annotations offer.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is 5 sentences, front-loaded with purpose. Each sentence adds value: purpose, usage guidance, sibling, auth, side effects, returns. It is fairly concise, though could be slightly more streamlined. Overall well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (public web search, payment, multiple auth methods, output schema exists), the description covers all essential aspects: purpose, usage, auth, side effects, and return types. No obvious gaps remain.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema descriptions cover all 3 parameters with 100% coverage. The description adds no additional parameter-specific meaning beyond what is already in the schema (e.g., query is a search string, max_results default 5, payment_signature optional). Baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states 'Run a public web search and return titles, URLs, and snippets as JSON.' It specifies the verb, resource, and output format. It distinguishes from sibling vc_page_markdown by noting that vc_web_search is for public web results, not private pages.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly states when to use ('when you need current public web results for a query') and when not to use ('Do not use for private/intranet pages') with a direct alternative ('call vc_page_markdown with a known URL instead'). It also names the sibling tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.